github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4788] Add EventSource for format /api/generate #49528

New Issue
Closed
opened 2026-04-28 12:07:21 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 12:07:21 -05:00
Owner
Copy Link

Originally created by @Vali-98 on GitHub (Jun 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4788

What is the issue?

This was tested specifically with /api/generate and react-native-sse.

https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events
Stream responses sent in ollama doesn't seem to conform to SSE specifications, and breaks when using it with EventSource-like libraries.

Having this implementation will help with frontends and systems which prefer the EventSource format.

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.1.39

Originally created by @Vali-98 on GitHub (Jun 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4788 ### What is the issue? This was tested specifically with `/api/generate` and `react-native-sse`. https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events Stream responses sent in ollama doesn't seem to conform to SSE specifications, and breaks when using it with EventSource-like libraries. Having this implementation will help with frontends and systems which prefer the EventSource format. ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.39
GiteaMirror added the bug label 2026-04-28 12:07:21 -05:00
GiteaMirror commented 2026-04-28 12:07:23 -05:00
Author
Owner
Copy Link

@Vali-98 commented on GitHub (Jul 3, 2024):

This should be solved with https://github.com/ollama/ollama/pull/5209.

<!-- gh-comment-id:2205241234 --> @Vali-98 commented on GitHub (Jul 3, 2024): This should be solved with https://github.com/ollama/ollama/pull/5209.
GiteaMirror commented 2026-04-28 12:07:24 -05:00
Author
Owner
Copy Link

@prantlf commented on GitHub (Jul 30, 2025):

This issue wasn't fixed. Ollama doesn't support SSE.

Streaming is supported by chunked encoding with the content type application/x-ndjson. For example:

curl -v -H 'Content-Type: application/json' \
  -d '{"model":"deepseek-r1:1.5b","messages":[{"role":"user","content":"what is ollama?"}]}' \
  http://localhost:11434/api/chat

< HTTP/1.1 200 OK
< Content-Type: application/x-ndjson
< Date: Wed, 30 Jul 2025 09:45:03 GMT
< Transfer-Encoding: chunked
<
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.537758Z","message":{"role":"assistant","content":"\n\n"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.654744Z","message":{"role":"assistant","content":"\u003c/think\u003e"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.76711Z","message":{"role":"assistant","content":"\n\n"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.877521Z","message":{"role":"assistant","content":"O"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.988219Z","message":{"role":"assistant","content":"ll"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:04.098806Z","message":{"role":"assistant","content":"ama"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:04.21934Z","message":{"role":"assistant","content":" is"},"done":false}
...
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:48.36868Z","message":{"role":"assistant","content":" setup"},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:48.517462Z","message":{"role":"assistant","content":"."},"done":false}
{"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:48.665553Z","message":{"role":"assistant","content":""},"done_reason":"stop","done":true,"total_duration":49729537151,"load_duration":3445259896,"prompt_eval_count":9,"prompt_eval_duration":1024746038,"eval_count":274,"eval_duration":45257702287}

The same response will be sent even of the client requests SSE by the header Accept: text/event-stream.

Until SSE is supported, other content types should be rejected with the status 415:

HTTP/1.1 415 Unsupported Media Type
Accept-Post: application/x-ndjson

The simplest SSE support can be added by prefixing each JSON object (chunk) with data: and ending it with two line breaks (\n). No need for the rest of the SSE protocl, at the beginning.

For example thi sis how Google Gemini supports streaming with SSE supports SSE:

POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse

< HTTP/2 200
< content-type: text/event-stream
<
data: {"candidates": ...}

data: {"candidates": ... "finishReason": "STOP" ...}
<!-- gh-comment-id:3135741284 --> @prantlf commented on GitHub (Jul 30, 2025): This issue wasn't fixed. Ollama doesn't support SSE. Streaming is supported by chunked encoding with the content type `application/x-ndjson`. For example: ``` curl -v -H 'Content-Type: application/json' \ -d '{"model":"deepseek-r1:1.5b","messages":[{"role":"user","content":"what is ollama?"}]}' \ http://localhost:11434/api/chat < HTTP/1.1 200 OK < Content-Type: application/x-ndjson < Date: Wed, 30 Jul 2025 09:45:03 GMT < Transfer-Encoding: chunked < {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.537758Z","message":{"role":"assistant","content":"\n\n"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.654744Z","message":{"role":"assistant","content":"\u003c/think\u003e"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.76711Z","message":{"role":"assistant","content":"\n\n"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.877521Z","message":{"role":"assistant","content":"O"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:03.988219Z","message":{"role":"assistant","content":"ll"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:04.098806Z","message":{"role":"assistant","content":"ama"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:04.21934Z","message":{"role":"assistant","content":" is"},"done":false} ... {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:48.36868Z","message":{"role":"assistant","content":" setup"},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:48.517462Z","message":{"role":"assistant","content":"."},"done":false} {"model":"deepseek-r1:1.5b","created_at":"2025-07-30T09:45:48.665553Z","message":{"role":"assistant","content":""},"done_reason":"stop","done":true,"total_duration":49729537151,"load_duration":3445259896,"prompt_eval_count":9,"prompt_eval_duration":1024746038,"eval_count":274,"eval_duration":45257702287} ``` The same response will be sent even of the client requests SSE by the header `Accept: text/event-stream`. Until SSE is supported, other content types should be [rejected with the status 415](https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Status/415): ``` HTTP/1.1 415 Unsupported Media Type Accept-Post: application/x-ndjson ``` The [simplest SSE support](https://html.spec.whatwg.org/multipage/server-sent-events.html#parsing-an-event-stream) can be added by prefixing each JSON object (chunk) with `data: ` and ending it with two line breaks (`\n`). No need for the rest of the SSE protocl, at the beginning. For example thi sis how [Google Gemini supports streaming with SSE](https://ai.google.dev/gemini-api/docs/text-generation) supports SSE: ``` POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse < HTTP/2 200 < content-type: text/event-stream < data: {"candidates": ...} data: {"candidates": ... "finishReason": "STOP" ...} ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#49528
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?